IcuCollation::isCjk() - Code Metrics - wikimedia/mediawiki - Measure and Improve Code Quality continuously with Scrutinizer

IcuCollation::isCjk() A
last analyzed 2016-11-13 17:42 UTC

↳ Parent: IcuCollation

Complexity

Conditions	4
Paths	3

Size

Total Lines	8
Code Lines	5

Duplication

Lines	0
Ratio	0 %

Importance

Changes

Metric	Value
cc	4
eloc	5
nc	3
nop	1
dl	0
loc	8
rs	9.2
c	0
b	0
f	0

<?php
/**
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License along
 * with this program; if not, write to the Free Software Foundation, Inc.,
 * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
 * http://www.gnu.org/copyleft/gpl.html
 *
 * @file
 */

/**
 * @since 1.16.3
 */
class IcuCollation extends Collation {
	const FIRST_LETTER_VERSION = 2;

	/** @var Collator */
	private $primaryCollator;

	/** @var Collator */
	private $mainCollator;

	/** @var string */
	private $locale;

	/** @var Language */
	protected $digitTransformLanguage;

	/** @var boolean */
	private $useNumericCollation = false;

	/** @var array */
	private $firstLetterData;

	/**
	 * Unified CJK blocks.
	 *
	 * The same definition of a CJK block must be used for both Collation and
	 * generateCollationData.php. These blocks are omitted from the first
	 * letter data, as an optimisation measure and because the default UCA table
	 * is pretty useless for sorting Chinese text anyway. Japanese and Korean
	 * blocks are not included here, because they are smaller and more useful.
	 */
	private static $cjkBlocks = [
		[ 0x2E80, 0x2EFF ], // CJK Radicals Supplement
		[ 0x2F00, 0x2FDF ], // Kangxi Radicals
		[ 0x2FF0, 0x2FFF ], // Ideographic Description Characters
		[ 0x3000, 0x303F ], // CJK Symbols and Punctuation
		[ 0x31C0, 0x31EF ], // CJK Strokes
		[ 0x3200, 0x32FF ], // Enclosed CJK Letters and Months
		[ 0x3300, 0x33FF ], // CJK Compatibility
		[ 0x3400, 0x4DBF ], // CJK Unified Ideographs Extension A
		[ 0x4E00, 0x9FFF ], // CJK Unified Ideographs
		[ 0xF900, 0xFAFF ], // CJK Compatibility Ideographs
		[ 0xFE30, 0xFE4F ], // CJK Compatibility Forms
		[ 0x20000, 0x2A6DF ], // CJK Unified Ideographs Extension B
		[ 0x2A700, 0x2B73F ], // CJK Unified Ideographs Extension C
		[ 0x2B740, 0x2B81F ], // CJK Unified Ideographs Extension D
		[ 0x2F800, 0x2FA1F ], // CJK Compatibility Ideographs Supplement
	];

	/**
	 * Additional characters (or character groups) to be considered separate
	 * letters for given languages, or to be removed from the list of such
	 * letters (denoted by keys starting with '-').
	 *
	 * These are additions to (or subtractions from) the data stored in the
	 * first-letters-root.ser file (which among others includes full basic latin,
	 * cyrillic and greek alphabets).
	 *
	 * "Separate letter" is a letter that would have a separate heading/section
	 * for it in a dictionary or a phone book in this language. This data isn't
	 * used for sorting (the ICU library handles that), only for deciding which
	 * characters (or character groups) to use as headings.
	 *
	 * Initially generated based on the primary level of Unicode collation
	 * tailorings available at http://developer.mimer.com/charts/tailorings.htm ,
	 * later modified.
	 *
	 * Empty arrays are intended; this signifies that the data for the language is
	 * available and that there are, in fact, no additional letters to consider.
	 */
	private static $tailoringFirstLetters = [
		'af' => [],
		'am' => [],
		'ar' => [],
		'as' => [ "\xe0\xa6\x82", "\xe0\xa6\x81", "\xe0\xa6\x83", "\xe0\xa7\x8e", "ক্ষ " ],
		'ast' => [ "Ch", "Ll", "Ñ" ], // not in libicu
		'az' => [ "Ç", "Ə", "Ğ", "İ", "Ö", "Ş", "Ü" ],
		'be' => [ "Ё" ],
		'be-tarask' => [ "Ё" ],
		'bg' => [],
		'bo' => [],
		'br' => [ "Ch", "C'h" ],
		'bs' => [ "Č", "Ć", "Dž", "Đ", "Lj", "Nj", "Š", "Ž" ],
		'bs-Cyrl' => [],
		'ca' => [],
		'chr' => [],
		'co' => [], // not in libicu
		'cs' => [ "Č", "Ch", "Ř", "Š", "Ž" ],
		'cy' => [ "Ch", "Dd", "Ff", "Ng", "Ll", "Ph", "Rh", "Th" ],
		'da' => [ "Æ", "Ø", "Å" ],
		'de' => [],
		'de-AT@collation=phonebook' => [ 'ä', 'ö', 'ü', 'ß' ],
		'dsb' => [ "Č", "Ć", "Dź", "Ě", "Ch", "Ł", "Ń", "Ŕ", "Š", "Ś", "Ž", "Ź" ],
		'ee' => [ "Dz", "Ɖ", "Ɛ", "Ƒ", "Gb", "Ɣ", "Kp", "Ny", "Ŋ", "Ɔ", "Ts", "Ʋ" ],
		'el' => [],
		'en' => [],
		'eo' => [ "Ĉ", "Ĝ", "Ĥ", "Ĵ", "Ŝ", "Ŭ" ],
		'es' => [ "Ñ" ],
		'et' => [ "Š", "Ž", "Õ", "Ä", "Ö", "Ü", "W" ], // added W for CollationEt (xx-uca-et)
		'eu' => [ "Ñ" ], // not in libicu
		'fa' => [
			// RTL, let's put each letter on a new line
			"آ",
			"ء",
			"ه",
			"ا",
			"و"
		],
		'fi' => [ "Å", "Ä", "Ö" ],
		'fil' => [ "Ñ", "Ng" ],
		'fo' => [ "Á", "Ð", "Í", "Ó", "Ú", "Ý", "Æ", "Ø", "Å" ],
		'fr' => [],
		'fr-CA' => [], // fr-CA sorts accents slightly different from fr.
		'fur' => [ "À", "Á", "Â", "È", "Ì", "Ò", "Ù" ], // not in libicu
		'fy' => [], // not in libicu
		'ga' => [],
		'gd' => [], // not in libicu
		'gl' => [ "Ch", "Ll", "Ñ" ],
		'gu' => [ "\xe0\xaa\x82", "\xe0\xaa\x83", "\xe0\xaa\x81", "\xe0\xaa\xb3" ],
		'ha' => [ 'Ɓ', 'Ɗ', 'Ƙ', 'Sh', 'Ts', 'Ƴ' ],
		'haw' => [ 'ʻ' ],
		'he' => [],
		'hi' => [ "\xe0\xa4\x82", "\xe0\xa4\x83" ],
		'hr' => [ "Č", "Ć", "Dž", "Đ", "Lj", "Nj", "Š", "Ž" ],
		'hsb' => [ "Č", "Dź", "Ě", "Ch", "Ł", "Ń", "Ř", "Š", "Ć", "Ž" ],
		'hu' => [ "Cs", "Dz", "Dzs", "Gy", "Ly", "Ny", "Ö", "Sz", "Ty", "Ü", "Zs" ],
		'hy' => [ "և" ],
		'id' => [],
		'ig' => [ "Ch", "Gb", "Gh", "Gw", "Ị", "Kp", "Kw", "Ṅ", "Nw", "Ny", "Ọ", "Sh", "Ụ" ],
		'is' => [ "Á", "Ð", "É", "Í", "Ó", "Ú", "Ý", "Þ", "Æ", "Ö", "Å" ],
		'it' => [],
		'ka' => [],
		'kk' => [ "Ү", "І" ],
		'kl' => [ "Æ", "Ø", "Å" ],
		'km' => [
			"រ", "ឫ", "ឬ", "ល", "ឭ", "ឮ", "\xe1\x9e\xbb\xe1\x9f\x86",
			"\xe1\x9f\x86", "\xe1\x9e\xb6\xe1\x9f\x86", "\xe1\x9f\x87",
			"\xe1\x9e\xb7\xe1\x9f\x87", "\xe1\x9e\xbb\xe1\x9f\x87",
			"\xe1\x9f\x81\xe1\x9f\x87", "\xe1\x9f\x84\xe1\x9f\x87",
		],
		'kn' => [ "\xe0\xb2\x81", "\xe0\xb2\x83", "\xe0\xb3\xb1", "\xe0\xb3\xb2" ],
		'kok' => [ "\xe0\xa4\x82", "\xe0\xa4\x83", "ळ", "क्ष" ],
		'ku' => [ "Ç", "Ê", "Î", "Ş", "Û" ], // not in libicu
		'ky' => [ "Ё" ],
		'la' => [], // not in libicu
		'lb' => [],
		'lkt' => [ 'Č', 'Ǧ', 'Ȟ', 'Š', 'Ž' ],
		'ln' => [ 'Ɛ' ],
		'lo' => [],
		'lt' => [ "Č", "Š", "Ž" ],
		'lv' => [ "Č", "Ģ", "Ķ", "Ļ", "Ņ", "Š", "Ž" ],
		'mk' => [ "Ѓ", "Ќ" ],
		'ml' => [],
		'mn' => [],
		'mo' => [ "Ă", "Â", "Î", "Ş", "Ţ" ], // not in libicu
		'mr' => [ "\xe0\xa4\x82", "\xe0\xa4\x83", "ळ", "क्ष", "ज्ञ" ],
		'ms' => [],
		'mt' => [ "Ċ", "Ġ", "Għ", "Ħ", "Ż" ],
		'nb' => [ "Æ", "Ø", "Å" ],
		'ne' => [],
		'nl' => [],
		'nn' => [ "Æ", "Ø", "Å" ],
		'no' => [ "Æ", "Ø", "Å" ], // not in libicu. You should probably use nb or nn instead.
		'oc' => [], // not in libicu
		'om' => [ 'Ch', 'Dh', 'Kh', 'Ny', 'Ph', 'Sh' ],
		'or' => [ "\xe0\xac\x81", "\xe0\xac\x82", "\xe0\xac\x83", "କ୍ଷ" ],
		'pa' => [ "\xe0\xa9\x8d" ],
		'pl' => [ "Ą", "Ć", "Ę", "Ł", "Ń", "Ó", "Ś", "Ź", "Ż" ],
		'pt' => [],
		'rm' => [], // not in libicu
		'ro' => [ "Ă", "Â", "Î", "Ş", "Ţ" ],
		'ru' => [],
		'rup' => [ "Ă", "Â", "Î", "Ľ", "Ń", "Ş", "Ţ" ], // not in libicu
		'sco' => [],
		'se' => [
			'Á', 'Č', 'Ʒ', 'Ǯ', 'Đ', 'Ǧ', 'Ǥ', 'Ǩ', 'Ŋ',
			'Š', 'Ŧ', 'Ž', 'Ø', 'Æ', 'Ȧ', 'Ä', 'Ö'
		],
		'si' => [ "\xe0\xb6\x82", "\xe0\xb6\x83", "\xe0\xb6\xa4" ],
		'sk' => [ "Ä", "Č", "Ch", "Ô", "Š", "Ž" ],
		'sl' => [ "Č", "Š", "Ž" ],
		'smn' => [ "Á", "Č", "Đ", "Ŋ", "Š", "Ŧ", "Ž", "Æ", "Ø", "Å", "Ä", "Ö" ],
		'sq' => [ "Ç", "Dh", "Ë", "Gj", "Ll", "Nj", "Rr", "Sh", "Th", "Xh", "Zh" ],
		'sr' => [],
		'sr-Latn' => [ "Č", "Ć", "Dž", "Đ", "Lj", "Nj", "Š", "Ž" ],
		'sv' => [ "Å", "Ä", "Ö" ],
		'sv@collation=standard' => [ "Å", "Ä", "Ö" ],
		'sw' => [],
		'ta' => [
			"\xE0\xAE\x82", "ஃ", "க்ஷ", "க்", "ங்", "ச்", "ஞ்", "ட்", "ண்", "த்", "ந்",
			"ப்", "ம்", "ய்", "ர்", "ல்", "வ்", "ழ்", "ள்", "ற்", "ன்", "ஜ்", "ஶ்", "ஷ்",
			"ஸ்", "ஹ்", "க்ஷ்"
		],
		'te' => [ "\xe0\xb0\x81", "\xe0\xb0\x82", "\xe0\xb0\x83" ],
		'th' => [ "ฯ", "\xe0\xb9\x86", "\xe0\xb9\x8d", "\xe0\xb8\xba" ],
		'tk' => [ "Ç", "Ä", "Ž", "Ň", "Ö", "Ş", "Ü", "Ý" ],
		'tl' => [ "Ñ", "Ng" ], // not in libicu
		'to' => [ "Ng", "ʻ" ],
		'tr' => [ "Ç", "Ğ", "İ", "Ö", "Ş", "Ü" ],
		'tt' => [ "Ә", "Ө", "Ү", "Җ", "Ң", "Һ" ], // not in libicu
		'uk' => [ "Ґ", "Ь" ],
		'uz' => [ "Ch", "G'", "Ng", "O'", "Sh" ], // not in libicu
		'vi' => [ "Ă", "Â", "Đ", "Ê", "Ô", "Ơ", "Ư" ],
		'vo' => [ "Ä", "Ö", "Ü" ],
		'yi' => [
			"\xd7\x91\xd6\xbf", "\xd7\x9b\xd6\xbc", "\xd7\xa4\xd6\xbc",
			"\xd7\xa9\xd7\x82", "\xd7\xaa\xd6\xbc"
		],
		'yo' => [ "Ẹ", "Gb", "Ọ", "Ṣ" ],
		'zu' => [],
	];

	/**
	 * @since 1.16.3
	 */
	const RECORD_LENGTH = 14;

	public function __construct( $locale ) {
		if ( !extension_loaded( 'intl' ) ) {
			throw new MWException( 'An ICU collation was requested, ' .
				'but the intl extension is not available.' );
		}

		$this->locale = $locale;
		// Drop everything after the '@' in locale's name
		$localeParts = explode( '@', $locale );
		$this->digitTransformLanguage = Language::factory( $locale === 'root' ? 'en' : $localeParts[0] );

		$this->mainCollator = Collator::create( $locale );
		if ( !$this->mainCollator ) {
			throw new MWException( "Invalid ICU locale specified for collation: $locale" );
		}

		$this->primaryCollator = Collator::create( $locale );
		$this->primaryCollator->setStrength( Collator::PRIMARY );

		// If the special suffix for numeric collation is present, turn on numeric collation.
		if ( substr( $locale, -5, 5 ) === '-u-kn' ) {
			$this->useNumericCollation = true;
			// Strip off the special suffix so it doesn't trip up fetchFirstLetterData().
			$this->locale = substr( $this->locale, 0, -5 );
			$this->mainCollator->setAttribute( Collator::NUMERIC_COLLATION, Collator::ON );
			$this->primaryCollator->setAttribute( Collator::NUMERIC_COLLATION, Collator::ON );
		}
	}

	public function getSortKey( $string ) {
		return $this->mainCollator->getSortKey( $string );
	}

	public function getPrimarySortKey( $string ) {
		return $this->primaryCollator->getSortKey( $string );
	}

	public function getFirstLetter( $string ) {
		$string = strval( $string );
		if ( $string === '' ) {
			return '';
		}

		$firstChar = mb_substr( $string, 0, 1, 'UTF-8' );

		// If the first character is a CJK character, just return that character.
		if ( ord( $firstChar ) > 0x7f && self::isCjk( UtfNormal\Utils::utf8ToCodepoint( $firstChar ) ) ) {
			return $firstChar;
		}

		$sortKey = $this->getPrimarySortKey( $string );

		// Do a binary search to find the correct letter to sort under
		$min = ArrayUtils::findLowerBound(
			[ $this, 'getSortKeyByLetterIndex' ],
			$this->getFirstLetterCount(),
			'strcmp',
			$sortKey );

		if ( $min === false ) {
			// Before the first letter
			return '';
		}

		$sortLetter = $this->getLetterByIndex( $min );

		if ( $this->useNumericCollation ) {
			// If the sort letter is a number, return '0–9' (or localized equivalent).
			// ASCII value of 0 is 48. ASCII value of 9 is 57.
			// Note that this also applies to non-Arabic numerals since they are
			// mapped to Arabic numeral sort letters. For example, ২ sorts as 2.
			if ( ord( $sortLetter ) >= 48 && ord( $sortLetter ) <= 57 ) {
				$sortLetter = wfMessage( 'category-header-numerals' )->numParams( 0, 9 )->text();
			}
		}
		return $sortLetter;
	}

	/**
	 * @since 1.16.3
	 * @return array
	 */
	public function getFirstLetterData() {
		if ( $this->firstLetterData === null ) {
			$cache = ObjectCache::getLocalServerInstance( CACHE_ANYTHING );
			$cacheKey = $cache->makeKey(
				'first-letters',
				$this->locale,
				$this->digitTransformLanguage->getCode(),
				self::getICUVersion(),
				self::FIRST_LETTER_VERSION
			);
			$this->firstLetterData = $cache->getWithSetCallback( $cacheKey, $cache::TTL_WEEK, function () {

				return $this->fetchFirstLetterData();
			} );
		}
		return $this->firstLetterData;
	}

	/**
	 * @return array
	 * @throws MWException
	 */
	private function fetchFirstLetterData() {
		// Generate data from serialized data file
		if ( isset( self::$tailoringFirstLetters[$this->locale] ) ) {
			$letters = wfGetPrecompiledData( 'first-letters-root.ser' );
			// Append additional characters
			$letters = array_merge( $letters, self::$tailoringFirstLetters[$this->locale] );
			// Remove unnecessary ones, if any
			if ( isset( self::$tailoringFirstLetters['-' . $this->locale] ) ) {
				$letters = array_diff( $letters, self::$tailoringFirstLetters['-' . $this->locale] );
			}
			// Apply digit transforms
			$digits = [ '0', '1', '2', '3', '4', '5', '6', '7', '8', '9' ];
			$letters = array_diff( $letters, $digits );
			foreach ( $digits as $digit ) {
				$letters[] = $this->digitTransformLanguage->formatNum( $digit, true );
			}
		} else {
			$letters = wfGetPrecompiledData( "first-letters-{$this->locale}.ser" );
			if ( $letters === false ) {
				throw new MWException( "MediaWiki does not support ICU locale " .
					"\"{$this->locale}\"" );
			}
		}

		/* Sort the letters.
		 *
		 * It's impossible to have the precompiled data file properly sorted,
		 * because the sort order changes depending on ICU version. If the
		 * array is not properly sorted, the binary search will return random
		 * results.
		 *
		 * We also take this opportunity to remove primary collisions.
		 */
		$letterMap = [];
		foreach ( $letters as $letter ) {
			$key = $this->getPrimarySortKey( $letter );
			if ( isset( $letterMap[$key] ) ) {
				// Primary collision
				// Keep whichever one sorts first in the main collator
				if ( $this->mainCollator->compare( $letter, $letterMap[$key] ) < 0 ) {
					$letterMap[$key] = $letter;
				}
			} else {
				$letterMap[$key] = $letter;
			}
		}
		ksort( $letterMap, SORT_STRING );

		/* Remove duplicate prefixes. Basically if something has a sortkey
		 * which is a prefix of some other sortkey, then it is an
		 * expansion and probably should not be considered a section
		 * header.
		 *
		 * For example 'þ' is sometimes sorted as if it is the letters
		 * 'th'. Other times it is its own primary element. Another
		 * example is '₨'. Sometimes its a currency symbol. Sometimes it
		 * is an 'R' followed by an 's'.
		 *
		 * Additionally an expanded element should always sort directly
		 * after its first element due to they way sortkeys work.
		 *
		 * UCA sortkey elements are of variable length but no collation
		 * element should be a prefix of some other element, so I think
		 * this is safe. See:
		 * - https://ssl.icu-project.org/repos/icu/icuhtml/trunk/design/collation/ICU_collation_design.htm
		 * - http://site.icu-project.org/design/collation/uca-weight-allocation
		 *
		 * Additionally, there is something called primary compression to
		 * worry about. Basically, if you have two primary elements that
		 * are more than one byte and both start with the same byte then
		 * the first byte is dropped on the second primary. Additionally
		 * either \x03 or \xFF may be added to mean that the next primary
		 * does not start with the first byte of the first primary.
		 *
		 * This shouldn't matter much, as the first primary is not
		 * changed, and that is what we are comparing against.
		 *
		 * tl;dr: This makes some assumptions about how icu implements
		 * collations. It seems incredibly unlikely these assumptions
		 * will change, but nonetheless they are assumptions.
		 */

		$prev = false;
		$duplicatePrefixes = [];
		foreach ( $letterMap as $key => $value ) {
			// Remove terminator byte. Otherwise the prefix
			// comparison will get hung up on that.
			$trimmedKey = rtrim( $key, "\0" );
			if ( $prev === false || $prev === '' ) {
				$prev = $trimmedKey;
				// We don't yet have a collation element
				// to compare against, so continue.
				continue;
			}

			// Due to the fact the array is sorted, we only have
			// to compare with the element directly previous
			// to the current element (skipping expansions).
			// An element "X" will always sort directly
			// before "XZ" (Unless we have "XY", but we
			// do not update $prev in that case).
			if ( substr( $trimmedKey, 0, strlen( $prev ) ) === $prev ) {
				$duplicatePrefixes[] = $key;
				// If this is an expansion, we don't want to
				// compare the next element to this element,
				// but to what is currently $prev
				continue;
			}
			$prev = $trimmedKey;
		}
		foreach ( $duplicatePrefixes as $badKey ) {
			wfDebug( "Removing '{$letterMap[$badKey]}' from first letters.\n" );
			unset( $letterMap[$badKey] );
			// This code assumes that unsetting does not change sort order.
		}
		$data = [
			'chars' => array_values( $letterMap ),
			'keys' => array_keys( $letterMap ),
		];

		// Reduce memory usage before caching
		unset( $letterMap );

		return $data;
	}

	/**
	 * @since 1.16.3
	 */
	public function getLetterByIndex( $index ) {
		return $this->getFirstLetterData()['chars'][$index];
	}

	/**
	 * @since 1.16.3
	 */
	public function getSortKeyByLetterIndex( $index ) {
		return $this->getFirstLetterData()['keys'][$index];
	}

	/**
	 * @since 1.16.3
	 */
	public function getFirstLetterCount() {
		return count( $this->getFirstLetterData()['chars'] );
	}

	/**
	 * Test if a code point is a CJK (Chinese, Japanese, Korean) character
	 * @since 1.16.3
	 */
	public static function isCjk( $codepoint ) {
		foreach ( self::$cjkBlocks as $block ) {
			if ( $codepoint >= $block[0] && $codepoint <= $block[1] ) {
				return true;
			}
		}
		return false;
	}

	/**
	 * Return the version of ICU library used by PHP's intl extension,
	 * or false when the extension is not installed of the version
	 * can't be determined.
	 *
	 * The constant INTL_ICU_VERSION this function refers to isn't really
	 * documented. It is available since PHP 5.3.7 (see PHP bug 54561).
	 * This function will return false on older PHPs.
	 *
	 * @since 1.21
	 * @return string|bool
	 */
	static function getICUVersion() {
		return defined( 'INTL_ICU_VERSION' ) ? INTL_ICU_VERSION : false;
	}

	/**
	 * Return the version of Unicode appropriate for the version of ICU library
	 * currently in use, or false when it can't be determined.
	 *
	 * @since 1.21
	 * @return string|bool
	 */
	static function getUnicodeVersionForICU() {
		$icuVersion = IcuCollation::getICUVersion();
		if ( !$icuVersion ) {
			return false;
		}

		$versionPrefix = substr( $icuVersion, 0, 3 );
		// Source: http://site.icu-project.org/download
		$map = [
			'57.' => '8.0',
			'56.' => '8.0',
			'55.' => '7.0',
			'54.' => '7.0',
			'53.' => '6.3',
			'52.' => '6.3',
			'51.' => '6.2',
			'50.' => '6.2',
			'49.' => '6.1',
			'4.8' => '6.0',
			'4.6' => '6.0',
			'4.4' => '5.2',
			'4.2' => '5.1',
			'4.0' => '5.1',
			'3.8' => '5.0',
			'3.6' => '5.0',
			'3.4' => '4.1',
		];

		if ( isset( $map[$versionPrefix] ) ) {
			return $map[$versionPrefix];
		} else {
			return false;
		}
	}
}


1			<?php
2			/**
3			* This program is free software; you can redistribute it and/or modify
4			* it under the terms of the GNU General Public License as published by
5			* the Free Software Foundation; either version 2 of the License, or
6			* (at your option) any later version.
7			*
8			* This program is distributed in the hope that it will be useful,
9			* but WITHOUT ANY WARRANTY; without even the implied warranty of
10			* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
11			* GNU General Public License for more details.
12			*
13			* You should have received a copy of the GNU General Public License along
14			* with this program; if not, write to the Free Software Foundation, Inc.,
15			* 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
16			* http://www.gnu.org/copyleft/gpl.html
17			*
18			* @file
19			*/
20
21			/**
22			* @since 1.16.3
23			*/
24			class IcuCollation extends Collation {
25			const FIRST_LETTER_VERSION = 2;
26
27			/** @var Collator */
28			private $primaryCollator;
29
30			/** @var Collator */
31			private $mainCollator;
32
33			/** @var string */
34			private $locale;
35
36			/** @var Language */
37			protected $digitTransformLanguage;
38
39			/** @var boolean */
40			private $useNumericCollation = false;
41
42			/** @var array */
43			private $firstLetterData;
44
45			/**
46			* Unified CJK blocks.
47			*
48			* The same definition of a CJK block must be used for both Collation and
49			* generateCollationData.php. These blocks are omitted from the first
50			* letter data, as an optimisation measure and because the default UCA table
51			* is pretty useless for sorting Chinese text anyway. Japanese and Korean
52			* blocks are not included here, because they are smaller and more useful.
53			*/
54			private static $cjkBlocks = [
55			[ 0x2E80, 0x2EFF ], // CJK Radicals Supplement
56			[ 0x2F00, 0x2FDF ], // Kangxi Radicals
57			[ 0x2FF0, 0x2FFF ], // Ideographic Description Characters
58			[ 0x3000, 0x303F ], // CJK Symbols and Punctuation
59			[ 0x31C0, 0x31EF ], // CJK Strokes
60			[ 0x3200, 0x32FF ], // Enclosed CJK Letters and Months
61			[ 0x3300, 0x33FF ], // CJK Compatibility
62			[ 0x3400, 0x4DBF ], // CJK Unified Ideographs Extension A
63			[ 0x4E00, 0x9FFF ], // CJK Unified Ideographs
64			[ 0xF900, 0xFAFF ], // CJK Compatibility Ideographs
65			[ 0xFE30, 0xFE4F ], // CJK Compatibility Forms
66			[ 0x20000, 0x2A6DF ], // CJK Unified Ideographs Extension B
67			[ 0x2A700, 0x2B73F ], // CJK Unified Ideographs Extension C
68			[ 0x2B740, 0x2B81F ], // CJK Unified Ideographs Extension D
69			[ 0x2F800, 0x2FA1F ], // CJK Compatibility Ideographs Supplement
70			];
71
72			/**
73			* Additional characters (or character groups) to be considered separate
74			* letters for given languages, or to be removed from the list of such
75			* letters (denoted by keys starting with '-').
76			*
77			* These are additions to (or subtractions from) the data stored in the
78			* first-letters-root.ser file (which among others includes full basic latin,
79			* cyrillic and greek alphabets).
80			*
81			* "Separate letter" is a letter that would have a separate heading/section
82			* for it in a dictionary or a phone book in this language. This data isn't
83			* used for sorting (the ICU library handles that), only for deciding which
84			* characters (or character groups) to use as headings.
85			*
86			* Initially generated based on the primary level of Unicode collation
87			* tailorings available at http://developer.mimer.com/charts/tailorings.htm ,
88			* later modified.
89			*
90			* Empty arrays are intended; this signifies that the data for the language is
91			* available and that there are, in fact, no additional letters to consider.
92			*/
93			private static $tailoringFirstLetters = [
94			'af' => [],
95			'am' => [],
96			'ar' => [],
97			'as' => [ "\xe0\xa6\x82", "\xe0\xa6\x81", "\xe0\xa6\x83", "\xe0\xa7\x8e", "ক্ষ " ],
98			'ast' => [ "Ch", "Ll", "Ñ" ], // not in libicu
99			'az' => [ "Ç", "Ə", "Ğ", "İ", "Ö", "Ş", "Ü" ],
100			'be' => [ "Ё" ],
101			'be-tarask' => [ "Ё" ],
102			'bg' => [],
103			'bo' => [],
104			'br' => [ "Ch", "C'h" ],
105			'bs' => [ "Č", "Ć", "Dž", "Đ", "Lj", "Nj", "Š", "Ž" ],
106			'bs-Cyrl' => [],
107			'ca' => [],
108			'chr' => [],
109			'co' => [], // not in libicu
110			'cs' => [ "Č", "Ch", "Ř", "Š", "Ž" ],
111			'cy' => [ "Ch", "Dd", "Ff", "Ng", "Ll", "Ph", "Rh", "Th" ],
112			'da' => [ "Æ", "Ø", "Å" ],
113			'de' => [],
114			'de-AT@collation=phonebook' => [ 'ä', 'ö', 'ü', 'ß' ],
115			'dsb' => [ "Č", "Ć", "Dź", "Ě", "Ch", "Ł", "Ń", "Ŕ", "Š", "Ś", "Ž", "Ź" ],
116			'ee' => [ "Dz", "Ɖ", "Ɛ", "Ƒ", "Gb", "Ɣ", "Kp", "Ny", "Ŋ", "Ɔ", "Ts", "Ʋ" ],
117			'el' => [],
118			'en' => [],
119			'eo' => [ "Ĉ", "Ĝ", "Ĥ", "Ĵ", "Ŝ", "Ŭ" ],
120			'es' => [ "Ñ" ],
121			'et' => [ "Š", "Ž", "Õ", "Ä", "Ö", "Ü", "W" ], // added W for CollationEt (xx-uca-et)
122			'eu' => [ "Ñ" ], // not in libicu
123			'fa' => [
124			// RTL, let's put each letter on a new line
125			"آ",
126			"ء",
127			"ه",
128			"ا",
129			"و"
130			],
131			'fi' => [ "Å", "Ä", "Ö" ],
132			'fil' => [ "Ñ", "Ng" ],
133			'fo' => [ "Á", "Ð", "Í", "Ó", "Ú", "Ý", "Æ", "Ø", "Å" ],
134			'fr' => [],
135			'fr-CA' => [], // fr-CA sorts accents slightly different from fr.
136			'fur' => [ "À", "Á", "Â", "È", "Ì", "Ò", "Ù" ], // not in libicu
137			'fy' => [], // not in libicu
138			'ga' => [],
139			'gd' => [], // not in libicu
140			'gl' => [ "Ch", "Ll", "Ñ" ],
141			'gu' => [ "\xe0\xaa\x82", "\xe0\xaa\x83", "\xe0\xaa\x81", "\xe0\xaa\xb3" ],
142			'ha' => [ 'Ɓ', 'Ɗ', 'Ƙ', 'Sh', 'Ts', 'Ƴ' ],
143			'haw' => [ 'ʻ' ],
144			'he' => [],
145			'hi' => [ "\xe0\xa4\x82", "\xe0\xa4\x83" ],
146			'hr' => [ "Č", "Ć", "Dž", "Đ", "Lj", "Nj", "Š", "Ž" ],
147			'hsb' => [ "Č", "Dź", "Ě", "Ch", "Ł", "Ń", "Ř", "Š", "Ć", "Ž" ],
148			'hu' => [ "Cs", "Dz", "Dzs", "Gy", "Ly", "Ny", "Ö", "Sz", "Ty", "Ü", "Zs" ],
149			'hy' => [ "և" ],
150			'id' => [],
151			'ig' => [ "Ch", "Gb", "Gh", "Gw", "Ị", "Kp", "Kw", "Ṅ", "Nw", "Ny", "Ọ", "Sh", "Ụ" ],
152			'is' => [ "Á", "Ð", "É", "Í", "Ó", "Ú", "Ý", "Þ", "Æ", "Ö", "Å" ],
153			'it' => [],
154			'ka' => [],
155			'kk' => [ "Ү", "І" ],
156			'kl' => [ "Æ", "Ø", "Å" ],
157			'km' => [
158			"រ", "ឫ", "ឬ", "ល", "ឭ", "ឮ", "\xe1\x9e\xbb\xe1\x9f\x86",
159			"\xe1\x9f\x86", "\xe1\x9e\xb6\xe1\x9f\x86", "\xe1\x9f\x87",
160			"\xe1\x9e\xb7\xe1\x9f\x87", "\xe1\x9e\xbb\xe1\x9f\x87",
161			"\xe1\x9f\x81\xe1\x9f\x87", "\xe1\x9f\x84\xe1\x9f\x87",
162			],
163			'kn' => [ "\xe0\xb2\x81", "\xe0\xb2\x83", "\xe0\xb3\xb1", "\xe0\xb3\xb2" ],
164			'kok' => [ "\xe0\xa4\x82", "\xe0\xa4\x83", "ळ", "क्ष" ],
165			'ku' => [ "Ç", "Ê", "Î", "Ş", "Û" ], // not in libicu
166			'ky' => [ "Ё" ],
167			'la' => [], // not in libicu
168			'lb' => [],
169			'lkt' => [ 'Č', 'Ǧ', 'Ȟ', 'Š', 'Ž' ],
170			'ln' => [ 'Ɛ' ],
171			'lo' => [],
172			'lt' => [ "Č", "Š", "Ž" ],
173			'lv' => [ "Č", "Ģ", "Ķ", "Ļ", "Ņ", "Š", "Ž" ],
174			'mk' => [ "Ѓ", "Ќ" ],
175			'ml' => [],
176			'mn' => [],
177			'mo' => [ "Ă", "Â", "Î", "Ş", "Ţ" ], // not in libicu
178			'mr' => [ "\xe0\xa4\x82", "\xe0\xa4\x83", "ळ", "क्ष", "ज्ञ" ],
179			'ms' => [],
180			'mt' => [ "Ċ", "Ġ", "Għ", "Ħ", "Ż" ],
181			'nb' => [ "Æ", "Ø", "Å" ],
182			'ne' => [],
183			'nl' => [],
184			'nn' => [ "Æ", "Ø", "Å" ],
185			'no' => [ "Æ", "Ø", "Å" ], // not in libicu. You should probably use nb or nn instead.
186			'oc' => [], // not in libicu
187			'om' => [ 'Ch', 'Dh', 'Kh', 'Ny', 'Ph', 'Sh' ],
188			'or' => [ "\xe0\xac\x81", "\xe0\xac\x82", "\xe0\xac\x83", "କ୍ଷ" ],
189			'pa' => [ "\xe0\xa9\x8d" ],
190			'pl' => [ "Ą", "Ć", "Ę", "Ł", "Ń", "Ó", "Ś", "Ź", "Ż" ],
191			'pt' => [],
192			'rm' => [], // not in libicu
193			'ro' => [ "Ă", "Â", "Î", "Ş", "Ţ" ],
194			'ru' => [],
195			'rup' => [ "Ă", "Â", "Î", "Ľ", "Ń", "Ş", "Ţ" ], // not in libicu
196			'sco' => [],
197			'se' => [
198			'Á', 'Č', 'Ʒ', 'Ǯ', 'Đ', 'Ǧ', 'Ǥ', 'Ǩ', 'Ŋ',
199			'Š', 'Ŧ', 'Ž', 'Ø', 'Æ', 'Ȧ', 'Ä', 'Ö'
200			],
201			'si' => [ "\xe0\xb6\x82", "\xe0\xb6\x83", "\xe0\xb6\xa4" ],
202			'sk' => [ "Ä", "Č", "Ch", "Ô", "Š", "Ž" ],
203			'sl' => [ "Č", "Š", "Ž" ],
204			'smn' => [ "Á", "Č", "Đ", "Ŋ", "Š", "Ŧ", "Ž", "Æ", "Ø", "Å", "Ä", "Ö" ],
205			'sq' => [ "Ç", "Dh", "Ë", "Gj", "Ll", "Nj", "Rr", "Sh", "Th", "Xh", "Zh" ],
206			'sr' => [],
207			'sr-Latn' => [ "Č", "Ć", "Dž", "Đ", "Lj", "Nj", "Š", "Ž" ],
208			'sv' => [ "Å", "Ä", "Ö" ],
209			'sv@collation=standard' => [ "Å", "Ä", "Ö" ],
210			'sw' => [],
211			'ta' => [
212			"\xE0\xAE\x82", "ஃ", "க்ஷ", "க்", "ங்", "ச்", "ஞ்", "ட்", "ண்", "த்", "ந்",
213			"ப்", "ம்", "ய்", "ர்", "ல்", "வ்", "ழ்", "ள்", "ற்", "ன்", "ஜ்", "ஶ்", "ஷ்",
214			"ஸ்", "ஹ்", "க்ஷ்"
215			],
216			'te' => [ "\xe0\xb0\x81", "\xe0\xb0\x82", "\xe0\xb0\x83" ],
217			'th' => [ "ฯ", "\xe0\xb9\x86", "\xe0\xb9\x8d", "\xe0\xb8\xba" ],
218			'tk' => [ "Ç", "Ä", "Ž", "Ň", "Ö", "Ş", "Ü", "Ý" ],
219			'tl' => [ "Ñ", "Ng" ], // not in libicu
220			'to' => [ "Ng", "ʻ" ],
221			'tr' => [ "Ç", "Ğ", "İ", "Ö", "Ş", "Ü" ],
222			'tt' => [ "Ә", "Ө", "Ү", "Җ", "Ң", "Һ" ], // not in libicu
223			'uk' => [ "Ґ", "Ь" ],
224			'uz' => [ "Ch", "G'", "Ng", "O'", "Sh" ], // not in libicu
225			'vi' => [ "Ă", "Â", "Đ", "Ê", "Ô", "Ơ", "Ư" ],
226			'vo' => [ "Ä", "Ö", "Ü" ],
227			'yi' => [
228			"\xd7\x91\xd6\xbf", "\xd7\x9b\xd6\xbc", "\xd7\xa4\xd6\xbc",
229			"\xd7\xa9\xd7\x82", "\xd7\xaa\xd6\xbc"
230			],
231			'yo' => [ "Ẹ", "Gb", "Ọ", "Ṣ" ],
232			'zu' => [],
233			];
234
235			/**
236			* @since 1.16.3
237			*/
238			const RECORD_LENGTH = 14;
239
240			public function __construct( $locale ) {
241			if ( !extension_loaded( 'intl' ) ) {
242			throw new MWException( 'An ICU collation was requested, ' .
243			'but the intl extension is not available.' );
244			}
245
246			$this->locale = $locale;
247			// Drop everything after the '@' in locale's name
248			$localeParts = explode( '@', $locale );
249			$this->digitTransformLanguage = Language::factory( $locale === 'root' ? 'en' : $localeParts[0] );
250
251			$this->mainCollator = Collator::create( $locale );
252			if ( !$this->mainCollator ) {
253			throw new MWException( "Invalid ICU locale specified for collation: $locale" );
254			}
255
256			$this->primaryCollator = Collator::create( $locale );
257			$this->primaryCollator->setStrength( Collator::PRIMARY );
258
259			// If the special suffix for numeric collation is present, turn on numeric collation.
260			if ( substr( $locale, -5, 5 ) === '-u-kn' ) {
261			$this->useNumericCollation = true;
262			// Strip off the special suffix so it doesn't trip up fetchFirstLetterData().
263			$this->locale = substr( $this->locale, 0, -5 );
264			$this->mainCollator->setAttribute( Collator::NUMERIC_COLLATION, Collator::ON );
265			$this->primaryCollator->setAttribute( Collator::NUMERIC_COLLATION, Collator::ON );
266			}
267			}
268
269			public function getSortKey( $string ) {
270			return $this->mainCollator->getSortKey( $string );
271			}
272
273			public function getPrimarySortKey( $string ) {
274			return $this->primaryCollator->getSortKey( $string );
275			}
276
277			public function getFirstLetter( $string ) {
278			$string = strval( $string );
279			if ( $string === '' ) {
280			return '';
281			}
282
283			$firstChar = mb_substr( $string, 0, 1, 'UTF-8' );
284
285			// If the first character is a CJK character, just return that character.
286			if ( ord( $firstChar ) > 0x7f && self::isCjk( UtfNormal\Utils::utf8ToCodepoint( $firstChar ) ) ) {
287			return $firstChar;
288			}
289
290			$sortKey = $this->getPrimarySortKey( $string );
291
292			// Do a binary search to find the correct letter to sort under
293			$min = ArrayUtils::findLowerBound(
294			[ $this, 'getSortKeyByLetterIndex' ],
295			$this->getFirstLetterCount(),
296			'strcmp',
297			$sortKey );
298
299			if ( $min === false ) {
300			// Before the first letter
301			return '';
302			}
303
304			$sortLetter = $this->getLetterByIndex( $min );
305
306			if ( $this->useNumericCollation ) {
307			// If the sort letter is a number, return '0–9' (or localized equivalent).
308			// ASCII value of 0 is 48. ASCII value of 9 is 57.
309			// Note that this also applies to non-Arabic numerals since they are
310			// mapped to Arabic numeral sort letters. For example, ২ sorts as 2.
311			if ( ord( $sortLetter ) >= 48 && ord( $sortLetter ) <= 57 ) {
312			$sortLetter = wfMessage( 'category-header-numerals' )->numParams( 0, 9 )->text();
313			}
314			}
315			return $sortLetter;
316			}
317
318			/**
319			* @since 1.16.3
320			* @return array
321			*/
322			public function getFirstLetterData() {
323			if ( $this->firstLetterData === null ) {
324			$cache = ObjectCache::getLocalServerInstance( CACHE_ANYTHING );
325			$cacheKey = $cache->makeKey(
326			'first-letters',
327			$this->locale,
328			$this->digitTransformLanguage->getCode(),
329			self::getICUVersion(),
330			self::FIRST_LETTER_VERSION
331			);
332			$this->firstLetterData = $cache->getWithSetCallback( $cacheKey, $cache::TTL_WEEK, function () {
			0 ignored issues – show Documentation Bug introduced 2016-05-12 17:50 UTC by Report Bug Copy Issue Report It seems like `$cache->getWithSetCallba...chFirstLetterData(); })` of type `*` is incompatible with the declared type `array` of property `$firstLetterData`. Our type inference engine has found an assignment to a property that is incompatible with the declared type of that property. Either this assignment is in error or the assigned type should be added to the documentation/type hint for that property.. Loading history...
333			return $this->fetchFirstLetterData();
334			} );
335			}
336			return $this->firstLetterData;
337			}
338
339			/**
340			* @return array
341			* @throws MWException
342			*/
343			private function fetchFirstLetterData() {
344			// Generate data from serialized data file
345			if ( isset( self::$tailoringFirstLetters[$this->locale] ) ) {
346			$letters = wfGetPrecompiledData( 'first-letters-root.ser' );
347			// Append additional characters
348			$letters = array_merge( $letters, self::$tailoringFirstLetters[$this->locale] );
349			// Remove unnecessary ones, if any
350			if ( isset( self::$tailoringFirstLetters['-' . $this->locale] ) ) {
351			$letters = array_diff( $letters, self::$tailoringFirstLetters['-' . $this->locale] );
352			}
353			// Apply digit transforms
354			$digits = [ '0', '1', '2', '3', '4', '5', '6', '7', '8', '9' ];
355			$letters = array_diff( $letters, $digits );
356			foreach ( $digits as $digit ) {
357			$letters[] = $this->digitTransformLanguage->formatNum( $digit, true );
358			}
359			} else {
360			$letters = wfGetPrecompiledData( "first-letters-{$this->locale}.ser" );
361			if ( $letters === false ) {
362			throw new MWException( "MediaWiki does not support ICU locale " .
363			"\"{$this->locale}\"" );
364			}
365			}
366
367			/* Sort the letters.
368			*
369			* It's impossible to have the precompiled data file properly sorted,
370			* because the sort order changes depending on ICU version. If the
371			* array is not properly sorted, the binary search will return random
372			* results.
373			*
374			* We also take this opportunity to remove primary collisions.
375			*/
376			$letterMap = [];
377			foreach ( $letters as $letter ) {
378			$key = $this->getPrimarySortKey( $letter );
379			if ( isset( $letterMap[$key] ) ) {
380			// Primary collision
381			// Keep whichever one sorts first in the main collator
382			if ( $this->mainCollator->compare( $letter, $letterMap[$key] ) < 0 ) {
383			$letterMap[$key] = $letter;
384			}
385			} else {
386			$letterMap[$key] = $letter;
387			}
388			}
389			ksort( $letterMap, SORT_STRING );
390
391			/* Remove duplicate prefixes. Basically if something has a sortkey
392			* which is a prefix of some other sortkey, then it is an
393			* expansion and probably should not be considered a section
394			* header.
395			*
396			* For example 'þ' is sometimes sorted as if it is the letters
397			* 'th'. Other times it is its own primary element. Another
398			* example is '₨'. Sometimes its a currency symbol. Sometimes it
399			* is an 'R' followed by an 's'.
400			*
401			* Additionally an expanded element should always sort directly
402			* after its first element due to they way sortkeys work.
403			*
404			* UCA sortkey elements are of variable length but no collation
405			* element should be a prefix of some other element, so I think
406			* this is safe. See:
407			* - https://ssl.icu-project.org/repos/icu/icuhtml/trunk/design/collation/ICU_collation_design.htm
408			* - http://site.icu-project.org/design/collation/uca-weight-allocation
409			*
410			* Additionally, there is something called primary compression to
411			* worry about. Basically, if you have two primary elements that
412			* are more than one byte and both start with the same byte then
413			* the first byte is dropped on the second primary. Additionally
414			* either \x03 or \xFF may be added to mean that the next primary
415			* does not start with the first byte of the first primary.
416			*
417			* This shouldn't matter much, as the first primary is not
418			* changed, and that is what we are comparing against.
419			*
420			* tl;dr: This makes some assumptions about how icu implements
421			* collations. It seems incredibly unlikely these assumptions
422			* will change, but nonetheless they are assumptions.
423			*/
424
425			$prev = false;
426			$duplicatePrefixes = [];
427			foreach ( $letterMap as $key => $value ) {
428			// Remove terminator byte. Otherwise the prefix
429			// comparison will get hung up on that.
430			$trimmedKey = rtrim( $key, "\0" );
431			if ( $prev === false \|\| $prev === '' ) {
432			$prev = $trimmedKey;
433			// We don't yet have a collation element
434			// to compare against, so continue.
435			continue;
436			}
437
438			// Due to the fact the array is sorted, we only have
439			// to compare with the element directly previous
440			// to the current element (skipping expansions).
441			// An element "X" will always sort directly
442			// before "XZ" (Unless we have "XY", but we
443			// do not update $prev in that case).
444			if ( substr( $trimmedKey, 0, strlen( $prev ) ) === $prev ) {
445			$duplicatePrefixes[] = $key;
446			// If this is an expansion, we don't want to
447			// compare the next element to this element,
448			// but to what is currently $prev
449			continue;
450			}
451			$prev = $trimmedKey;
452			}
453			foreach ( $duplicatePrefixes as $badKey ) {
454			wfDebug( "Removing '{$letterMap[$badKey]}' from first letters.\n" );
455			unset( $letterMap[$badKey] );
456			// This code assumes that unsetting does not change sort order.
457			}
458			$data = [
459			'chars' => array_values( $letterMap ),
460			'keys' => array_keys( $letterMap ),
461			];
462
463			// Reduce memory usage before caching
464			unset( $letterMap );
465
466			return $data;
467			}
468
469			/**
470			* @since 1.16.3
471			*/
472			public function getLetterByIndex( $index ) {
473			return $this->getFirstLetterData()['chars'][$index];
474			}
475
476			/**
477			* @since 1.16.3
478			*/
479			public function getSortKeyByLetterIndex( $index ) {
480			return $this->getFirstLetterData()['keys'][$index];
481			}
482
483			/**
484			* @since 1.16.3
485			*/
486			public function getFirstLetterCount() {
487			return count( $this->getFirstLetterData()['chars'] );
488			}
489
490			/**
491			* Test if a code point is a CJK (Chinese, Japanese, Korean) character
492			* @since 1.16.3
493			*/
494			public static function isCjk( $codepoint ) {
495			foreach ( self::$cjkBlocks as $block ) {
496			if ( $codepoint >= $block[0] && $codepoint <= $block[1] ) {
497			return true;
498			}
499			}
500			return false;
501			}
502
503			/**
504			* Return the version of ICU library used by PHP's intl extension,
505			* or false when the extension is not installed of the version
506			* can't be determined.
507			*
508			* The constant INTL_ICU_VERSION this function refers to isn't really
509			* documented. It is available since PHP 5.3.7 (see PHP bug 54561).
510			* This function will return false on older PHPs.
511			*
512			* @since 1.21
513			* @return string\|bool
514			*/
515			static function getICUVersion() {
516			return defined( 'INTL_ICU_VERSION' ) ? INTL_ICU_VERSION : false;
517			}
518
519			/**
520			* Return the version of Unicode appropriate for the version of ICU library
521			* currently in use, or false when it can't be determined.
522			*
523			* @since 1.21
524			* @return string\|bool
525			*/
526			static function getUnicodeVersionForICU() {
527			$icuVersion = IcuCollation::getICUVersion();
528			if ( !$icuVersion ) {
529			return false;
530			}
531
532			$versionPrefix = substr( $icuVersion, 0, 3 );
533			// Source: http://site.icu-project.org/download
534			$map = [
535			'57.' => '8.0',
536			'56.' => '8.0',
537			'55.' => '7.0',
538			'54.' => '7.0',
539			'53.' => '6.3',
540			'52.' => '6.3',
541			'51.' => '6.2',
542			'50.' => '6.2',
543			'49.' => '6.1',
544			'4.8' => '6.0',
545			'4.6' => '6.0',
546			'4.4' => '5.2',
547			'4.2' => '5.1',
548			'4.0' => '5.1',
549			'3.8' => '5.0',
550			'3.6' => '5.0',
551			'3.4' => '4.1',
552			];
553
554			if ( isset( $map[$versionPrefix] ) ) {
555			return $map[$versionPrefix];
556			} else {
557			return false;
558			}
559			}
560			}
561

wikimedia / mediawiki

IcuCollation::isCjk() A last analyzed 2016-11-13 17:42 UTC

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like

IcuCollation::isCjk() A
last analyzed 2016-11-13 17:42 UTC